Chart Erratum and Refactoring

1. A computer-implemented method, comprising: evaluating, by one or more processors, a specimen chart relative to a chart erratum model comprising features mapped to an optimum state for a first chart type; generating a first risk score for a first sample feature of the specimen chart, wherein the first risk score comprises a delta from the optimum state; and refactoring the specimen chart to mitigate the first risk score of the first sample feature.

2. The method of claim 1 , comprising analyzing a plurality of charts to extract a pattern, wherein the pattern comprises a plurality of chart types defined by features.

3. The method of claim 2 , comprising mapping the features to optimum states for each chart type.

4. The method of claim 2 , wherein analyzing the plurality of charts comprises training a selection from the group consisting of a convolutional neural network and a support-vector machine.

5. The method of claim 1 , wherein the first chart type is selected from the group consisting of a bar chart, a line graph, a table, and a pie chart.

6. The method of claim 1 , wherein refactoring the specimen chart comprises labeling the first sample feature with a numerated risk score.

7. The method of claim 1 , wherein refactoring the specimen chart comprises a selection from the group consisting of highlighting the first sample feature and changing an appearance of the first sample feature.

8. The method of claim 1 , comprising: generating a second risk score for a second sample feature; and generating an overall risk score for the specimen chart based on the first risk score and the second risk score.

9. A computer program product comprising: one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising: evaluating, by one or more processors, a specimen chart relative to a chart erratum model comprising features mapped to an optimum state for a first chart type; generating a first risk score for a first sample feature of the specimen chart, wherein the first risk score comprises a delta from the optimum state; and refactoring the specimen chart to mitigate the first risk score of the first sample feature.

10. The computer program product of claim 9 , wherein the program instructions comprise analyzing a plurality of charts to extract a pattern, wherein the pattern comprises a plurality of chart types defined by features.

11. The computer program product of claim 10 , wherein the program instructions comprise mapping the features to optimum states for each chart type.

12. The computer program product of claim 10 , wherein analyzing the plurality of charts comprises training a selection from the group consisting of a convolutional neural network and a support-vector machine.

13. The computer program product of claim 9 , wherein the first chart type is selected from the group consisting of a bar chart, a line graph, a table, and a pie chart.

14. The computer program product of claim 9 , wherein refactoring the specimen chart comprises labeling the first sample feature with a numerated risk score.

15. The computer program product of claim 9 , wherein refactoring the specimen chart comprises a selection from the group consisting of highlighting the first sample feature and changing an appearance of the first sample feature.

16. The computer program product of claim 9 , wherein the program instructions comprise: generating a second risk score for a second sample feature; and generating an overall risk score for the specimen chart based on the first risk score and the second risk score.

17. A computer system comprising: one or more computer processors, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising: evaluating, by one or more processors, a specimen chart relative to a chart erratum model comprising features mapped to an optimum state for a first chart type; generating a first risk score for a first sample feature of the specimen chart, wherein the first risk score comprises a delta from the optimum state; and refactoring the specimen chart to mitigate the first risk score of the first sample feature.

18. The computer system of claim 17 , wherein the program instructions comprise: analyzing a plurality of charts to extract a pattern, wherein the pattern comprises a plurality of chart types defined by features; and mapping the features to optimum states for each chart type.

19. The computer system of claim 17 , wherein refactoring the specimen chart comprises a selection from the group consisting of labeling the first sample feature with a numerated risk score, highlighting the first sample feature, and changing an appearance of the first sample feature.

20. The computer system of claim 17 , wherein the program instructions comprise: generating a second risk score for a second sample feature; and generating an overall risk score for the specimen chart based on the first risk score and the second risk score.